Tomohiro Hayase

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 14

Top Topics

Fisher Information

Layer Perceptron

Top Venues

Publications

Tomohiro Hayase, Braun Sacha, Hikari Yanagawa, Itsuki Orito, Yuichi Hiroi
PanoTree: Autonomous Photo-Spot Explorer in Virtual Reality Scenes. CoRR (2024)
Michikuni Eguchi, Madoka Ito, Tomohiro Hayase, Yuichi Hiroi, Takefumi Hiraki
Cluster Haptic Texture Database: Haptic Texture Database with Variety in Velocity and Direction of Sliding Contacts. CoRR (2024)
Tomohiro Hayase, Ryo Karakida
MLP-Mixer as a Wide and Sparse MLP. CoRR (2023)
Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa
Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias. ICML (2023)
Ryo Karakida, Tomoumi Takase, Tomohiro Hayase, Kazuki Osawa
Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias. CoRR (2022)
Tomohiro Hayase, Suguru Yasutomi, Nakamasa Inoue
Downstream Augmentation Generation For Contrastive Learning. ICASSP (2022)
Tomohiro Hayase, Ryo Karakida
The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry. AISTATS (2021)
Shohei Kubota, Hideaki Hayashi, Tomohiro Hayase, Seiichi Uchida
Layer-Wise Interpretation of Deep Neural Networks Using Identity Initialization. CoRR (2021)
Takefumi Hiraki, Tomohiro Hayase, Yuichi Ike, Takashi Tsuboi, Michio Yoshiwaki
Viewpoint Planning of Projector Placement for Spatial Augmented Reality using Star-Kernel Decomposition. VR Workshops (2021)
Benoit Collins, Tomohiro Hayase
Asymptotic Freeness of Layerwise Jacobians Caused by Invariance of Multilayer Perceptron: The Haar Orthogonal Case. CoRR (2021)
Shohei Kubota, Hideaki Hayashi, Tomohiro Hayase, Seiichi Uchida
Layer-Wise Interpretation of Deep Neural Networks using Identity Initialization. ICASSP (2021)
Tomohiro Hayase, Suguru Yasutomi, Takashi Katoh
Selective Forgetting of Deep Networks at a Finer Level than Samples. CoRR (2020)
Tomohiro Hayase, Ryo Karakida
The Spectrum of Fisher Information of Deep Networks Achieving Dynamical Isometry. CoRR (2020)
Tomohiro Hayase
Cauchy noise loss for stochastic optimization of random matrix models via free deterministic equivalents. CoRR (2018)